Monday, August 9, 2010

Nominal, Ordinal and Scale variables

I CAN categorize but I CANNOT rank them in any relative order like say colors, gender, fruits, elements, etc. This means I am dealing with categorical variables. Categorical variables are sometimes called nominal variables.


I CAN categorize and I CAN rank them in a relative order but I CANNOT define the distance between them like say ranks in class, level of education, fruits, economic status, three categories (low, medium and high), etc. This means I am dealing with ordinal variables.


I CAN categorize and I CAN rank them in a relative order and I CAN define the distance between them like say annual income that is measured in dollars, and we have three people who make $10,000, $15,000 and $20,000, height, weight, etc.This means I am dealing with scale variables.

Does it matter what kind a variable is ?

Statistics assumes that the variables have a specific level of measurement. For example, it would not make sense to compute an average gender or a median color. Mean of a categorical variable does not make sense because there is no fundamental ordering of the ranks of the categories. So specifying the kind of variable lends meaning to statistics.